Video generation method and device, storage medium and program product

Abstract

The embodiment of the invention provides a video generation method and device, a storage medium and a program product. In the video generation method, in response to a video editing operation, editing demand description information can be obtained, copywriting information required for editing a video is automatically generated according to the editing demand description information, and at least one candidate video template matched with the editing demand description information and / or the copywriting information is output for a user to select. According to the target video template and the copywriting information, the target video can be automatically edited for the user, so that the labor cost and the technical threshold required by video editing are greatly reduced. Furthermore, the user does not need to manually execute complex editing operation with a relatively high technical threshold in a complex video editing page. When the method is applied to a housekeeping service scene, more housekeeping practitioners can easily and efficiently create an attractive propaganda video, thereby better popularizing own services.

Description

Technical Field

[0001] The present application relates to the field of Internet technology, and in particular to a video generation method, device, storage medium and program product. Background Art

[0002] In the domestic service scenario, as consumers' requirements for service quality continue to increase, more and more domestic service companies and individual practitioners have begun to use high-quality marketing videos to showcase service content and promote their services through Internet platforms. However, there are many challenges for domestic service practitioners in making marketing videos. In a traditional solution for making marketing videos, it is necessary to rely on a professional video production team, including screenwriters, directors, photographers, editors and other professionals. This solution has a high labor cost and is not friendly to most small and medium-sized domestic service companies or individual practitioners. With the development of the video industry, some popular video editing software has appeared on the market. This video editing software has a complex user interface and operation process, which has a high technical threshold for practitioners in the domestic industry. Therefore, a new solution needs to be proposed. Summary of the invention

[0003] Multiple aspects of the present application provide a video generation method, device, storage medium and program product to reduce the technical threshold required for video generation.

[0004] An embodiment of the present application provides a video generation method, including: responding to a video editing operation, obtaining editing requirement description information, wherein the editing requirement description information is used to describe the expected editing effect from multiple dimensions; based on the editing requirement description information, calling a content generation model to generate text information required for editing the video; outputting at least one candidate video template, wherein the at least one candidate video template is adapted to the editing requirement description information and / or the text information; responding to a selection operation on the at least one candidate video template, determining a selected target video template, and obtaining a target video material adapted to the target video template; and editing the text information and the target video material according to preset elements contained in the target video template to obtain a target video.

[0005] Optionally, obtaining the editing requirement description information includes: obtaining a voice message input by a user, and parsing information associated with the video editing requirement from the voice message to obtain the editing requirement description information; or, displaying a text configuration page, and obtaining the editing requirement description information based on the user's configuration operations on the text configuration page.

[0006] Optionally, a copy configuration page is displayed, and according to the configuration operations of the user on the copy configuration page, the editing requirement description information is obtained, including: displaying multiple configuration items on the copy configuration page, the multiple configuration items including: store logo, script style, service direction, service type, service area and multiple service advantages; according to the configuration operations of the user on the multiple configuration items on the copy configuration page, the configuration content of each of the multiple configuration items is obtained as the editing requirement description information.

[0007] Optionally, based on the editing requirement description information, a content generation model is called to generate text information required for editing the video, including: according to the structure of the multiple configuration items in the text configuration page, the configuration content of each of the multiple configuration items is converted into structured prompt words; based on the structured prompt words, the content generation model is called so that the content generation model generates the text information according to the structured prompt words.

[0008] Optionally, before displaying at least one candidate video template, it also includes: if the editing requirement description information includes a script style, selecting at least one candidate video template that is adapted to the script style from multiple video templates of different styles; and / or, identifying text attributes of the copy information, and selecting at least one candidate video template that is adapted to the text attributes from the multiple video templates, the text attributes including: text length, content theme, keyword density, and at least one of visual aid requirements.

[0009] Optionally, obtaining target video material that is adapted to the target video template includes: responding to a video material selection operation, obtaining video material submitted by a user according to material requirements corresponding to the target video template, as the target video material; and / or obtaining, from a material library, video material that is adapted to the editing requirement description information and / or the text information and meets the material requirements of the target video template, as the target video material.

[0010] Optionally, the text information and the target video material are edited according to preset elements contained in the target video template to obtain a target video, including: filling the placeholders in the target video template with the target video material according to the timeline layout of the target video template to obtain an initial editing result; converting the text information into subtitles and / or audio material according to the subtitle style and / or audio style in the target video template, and adding the subtitles and / or importing the audio track corresponding to the audio material to the initial editing result; and adding special effects to the initial editing result according to at least one special effect element set in the target video template.

[0011] Optionally, after the text information and the target video material are edited according to the preset elements contained in the target video template to obtain the target video, it also includes: displaying at least one publishing control, different publishing controls corresponding to different social platforms; responding to a triggering operation of a target publishing control in the at least one publishing control, publishing the target video to the target social platform through the interface of the social platform corresponding to the target publishing control.

[0012] An embodiment of the present application also provides an electronic device, comprising: a memory and a processor; the memory is used to store one or more computer instructions; the processor is used to execute the one or more computer instructions to: execute the steps in the method provided in the embodiment of the present application.

[0013] The embodiment of the present application also provides a computer-readable storage medium storing a computer program, which can implement the steps in the method provided in the embodiment of the present application when the computer program is executed by a processor.

[0014] The embodiment of the present application also provides a computer program product, including: a computer program / instructions, which, when executed by a processor, can implement the steps in the method provided in the embodiment of the present application.

[0015] In an embodiment of the present application, in response to a video editing operation, the editing requirement description information can be obtained, the text information required for editing the video can be automatically generated based on the editing requirement description information, and at least one candidate video template adapted to the editing requirement description information and / or the text information can be output for user selection. For users, when there is a need for video editing, video editing can be achieved by providing the editing requirement description information and selecting a target video template from the candidate video templates, and there is no need to manually perform complex editing operations with high technical barriers in a complex video editing page. According to the target video template and the text information, the target video can be automatically edited for the user, greatly reducing the labor cost and technical threshold required for video editing. When this video generation method is applied to the domestic service scenario, it can enable more domestic practitioners to easily and efficiently create attractive promotional videos, thereby better promoting their services. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0017] Figure 1 A schematic diagram of a flow chart of a video generation method provided by an exemplary embodiment of the present application;

[0018] Figure 2A schematic diagram of displaying multiple configuration items on a document configuration page provided for an exemplary embodiment of the present application;

[0019] Figure 3 A schematic diagram of a material selection page corresponding to a display material path provided by an exemplary embodiment of the present application;

[0020] Figure 4 A schematic diagram of the structure of an electronic device provided as an exemplary embodiment of the present application. DETAILED DESCRIPTION

[0021] In order to make the purpose, technical solution and advantages of the present application clearer, the technical solution of the present application will be clearly and completely described below in combination with the specific embodiments of the present application and the corresponding drawings. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present application.

[0022] The terms used in the embodiments of the present invention are only for the purpose of describing specific embodiments, and are not intended to limit the present invention. The singular forms "a", "said" and "the" used in the embodiments of the present invention and the appended claims are also intended to include plural forms, unless the context clearly indicates other meanings, and "multiple" generally includes at least two, but does not exclude the inclusion of at least one.

[0023] It should be understood that the term "and / or" used in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship.

[0024] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a product or system including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such a product or system. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the presence of other identical elements in the product or system including the element.

[0025] In view of the technical problem that existing video editing software has a high technical threshold, a solution is provided in some embodiments of the present application. The technical solutions provided by each embodiment of the present application are described in detail below in conjunction with the accompanying drawings.

[0026] Figure 1is a flow chart of a video generation method provided by an exemplary embodiment of the present application, the method may include: Figure 1 Steps shown:

[0027] Step 101: In response to a video editing operation, obtain editing requirement description information, where the editing requirement description information is used to describe the expected editing effect from multiple dimensions.

[0028] Step 102: Based on the editing requirement description information, a content generation model is called to generate text information required for editing the video.

[0029] Step 103: output at least one candidate video template, where the at least one candidate video template is adapted to the editing requirement description information and / or the text information.

[0030] Step 104: In response to the selection operation of the at least one candidate video template, determine the selected target video template, and obtain a target video material that matches the target video template.

[0031] Step 105: Edit the text information and the target video material according to the preset elements included in the target video template to obtain the target video.

[0032] This embodiment can be executed by an electronic device, and a tool for executing the video generation method can be run on the electronic device, hereinafter referred to as a video generation tool. The video generation tool can be a client application, a web program, or a backend service, which can be determined by the implementation form of the electronic device. For example, in some embodiments, the electronic device is implemented as a terminal device such as a desktop computer, a laptop computer, or a smart phone, and the video generation tool can be implemented as a client application running on the above terminal device or a functional module in the client application. The video generation tool can independently execute the video generation method on the terminal device, or can cooperate with the corresponding server program to execute the video generation method.

[0033] In other embodiments, the electronic device is implemented as a server-side device such as a conventional server, a cloud server or a server array, and the video generation tool can be implemented as a back-end service running on the server-side device, which can provide video generation services to other applications through an open interface. In some optional embodiments, the video generation tool can be implemented as a web program in which the front-end component runs in a browser on a terminal device and the back-end component runs on a server, and the front-end component and the back-end component of the web program can collaboratively execute the video generation method. In some application scenarios, the video generation method provided in the embodiment of the present application can be used to make promotional videos in the housekeeping service industry. In this type of application scenario, the video generation tool can be implemented as a functional module in the housekeeping client used by housekeeping practitioners, so that housekeeping practitioners can make promotional videos through the housekeeping client.

[0034] The following will provide a specific exemplary description of the video generation method performed by the video generation tool in combination with the above steps.

[0035] In step 101, the video generation tool may respond to the video editing operation and obtain the editing requirement description information. Optionally, the video editing operation may be initiated by the user, or may be initiated by a system event, which will be described below in conjunction with different embodiments. In some optional embodiments, the electronic device is implemented as a terminal device, and the terminal device may display the video editing page of the client program corresponding to the video generation tool, or the terminal device may display the video editing page of the front-end component corresponding to the video generation tool through a browser. The terminal device can detect the video editing operation by detecting the user's operation on the video editing page. In this embodiment, the user refers to a user who has a video editing demand, such as a housekeeping practitioner in a housekeeping service scenario.

[0036] In other optional embodiments, when the electronic device is implemented as a server-side device, a backend service corresponding to the video generation tool or a backend component corresponding to the video generation tool is running on the server-side device. The above-mentioned backend service or backend component can provide an API (Application Programming Interface) to the outside world, and can detect video editing operations by detecting call events to the API. Among them, the call event to the API can be initiated by other applications or systems. For example, in an application scenario in the housekeeping service industry, the housekeeping client automatically calls the above-mentioned API to initiate a video editing operation after detecting that the housekeeping practitioner has completed the store registration.

[0037] In this embodiment, the editing requirement description information is used to describe the expected editing effect from multiple dimensions, mainly including the user's intention, goal and expectation of editing the video. The editing requirement description information can be provided by the user, or can be obtained by the video generation tool from the user's historical service information or registration information.

[0038] In some optional embodiments, the video generation tool can obtain a voice message input by the user, and parse the voice message to obtain information associated with the video editing requirement, and obtain the editing requirement description information. Optionally, when the video generation tool is running on a terminal device or partially running on a terminal device, a voice input control can be displayed through the terminal device, and the voice message input by the user can be obtained through the microphone device on the terminal device in response to the user's triggering operation on the voice input control.

[0039] Optionally, in the process of parsing the information associated with the video editing requirement from the voice message, the video generation tool may pre-process the voice message to remove background noise and other interference signals and improve the voice quality. Afterwards, audio segmentation is performed on the pre-processed voice message to segment the long voice segment into shorter voice segments for subsequent processing. For each voice segment, the video generation tool may use the Speech-to-Text (STT) algorithm to convert the voice segment into a text segment. For each text segment, spelling checking and automatic correction may be performed to reduce errors caused by unclear pronunciation. Afterwards, the corrected text segment may be used to identify the intent through NLP technology to parse out the information associated with the video editing requirement. In the application scenario of the domestic service industry, for domestic practitioners, they only need to input a voice message containing the video editing requirement to provide the editing requirement description information, and do not need to perform complex description information input operations.

[0040] In other optional embodiments, when the video generation tool is running on a terminal device or partially running on a terminal device, the text configuration page can be displayed through the terminal device, and the editing requirement description information can be obtained according to the configuration operation of the user on the text configuration page. In this embodiment, the text configuration page can provide an intuitive user operation entrance so that the user can accurately provide the editing requirement description information.

[0041] Optionally, when the video generation tool displays the copy configuration page and obtains the editing requirement description information based on the configuration operation of the user on the copy configuration page, it can display multiple configuration items on the copy configuration page. The multiple configuration items include: store logo, script style, service direction, service type, service area, and service advantages. The video generation tool can obtain the configuration content of multiple configuration items as the editing requirement description information based on the configuration operation of the user on the copy configuration page. A typical copy configuration page can be as follows: Figure 2 As shown, it may include store name, script style, service direction, service type, service area, and service selling point, etc. For some configuration items, such as script style and service selling point, the video generation tool can provide multiple candidate configuration contents to facilitate user quick configuration.

[0042] Based on this implementation, the configuration items can be used to intuitively and clearly prompt the user with the content that needs to be input, thereby facilitating the acquisition of accurate editing requirement description information.

[0043] After obtaining the editing requirement description information based on the above implementation, in step 102, the video generation tool can call the content generation model according to the editing requirement description information to generate the text information required for editing the video.

[0044] In this embodiment, the content generation model may be an artificial intelligence (AI) model with content generation capabilities. Optionally, the AI ​​content generation model may be a large language model, which is a large language processing (NLP) model that has been trained on a large scale. Large language models are usually built based on deep learning technology and trained on large-scale training data sets, so that they can show strong performance when processing natural language tasks. Given a piece of text (i.e., context), the large language model will try to predict the words that are most likely to appear next. The number of parameters of the large language model is greater than the set threshold, which is usually on the order of millions or billions. During the training process, these parameters are continuously adjusted and optimized according to the difference between the predicted results of the large language model and the actual results to improve the prediction accuracy of the large language model. In some embodiments, the large language model usually uses an advanced neural network architecture, such as a Transformer architecture, to build a model structure, which enables the large language model to capture complex patterns in the text and handle long-distance dependencies. After sufficient training, the large language model has a strong generation capability and can produce coherent and contextual text content based on given prompts.

[0045] In this embodiment, a large language model pre-trained on a large number of general data sets can be used as the base model of the content generation model. In order to adapt to the specific application scenario of this application, that is, for generating the text information required for editing videos, the pre-trained large language model can be fine-tuned on a large number of data sets formed by video texts / scripts, so that the fine-tuned large language model is more suitable for performing the task of generating text information. In some optional embodiments, when the video generation tool calls the content generation model according to the editing requirement description information and generates the text information required for editing the video, it can convert the configuration content of each of the multiple configuration items into structured prompt words according to the structure of the multiple configuration items in the text configuration page, and call the content generation model according to the structured prompt words, so that the content generation model generates the text information according to the structured prompt words.

[0046] In this embodiment, the structure of multiple configuration items in the text configuration page refers to at least one of the logical grouping, hierarchy and priority sorting of multiple configuration items. Among them, logical grouping refers to classifying configuration items related to functions or attributes together. Hierarchy refers to the embodiment of major configuration items and minor configuration items through visual hierarchy and layout. Among them, priority sorting refers to sorting according to the importance of configuration items. After obtaining the configuration content of each of the multiple configuration items, the video generation tool can directly organize the configuration information of each of the multiple configuration items according to the structure of the multiple configuration items in the text configuration page to obtain structured prompt words. On the one hand, prompt words can be automatically and efficiently generated to speed up the configuration speed of prompt words. On the other hand, the readability of prompt words can be improved through structured processing, reducing the risk of ambiguity in natural language, and ensuring that each configuration item can be correctly understood and used by the content generation model.

[0047] In the content generation model, the input prompt word can be converted into a vector representation that the model can understand through the word segmenter to obtain an encoding vector. The content generation model can perform forward propagation calculations based on the encoding vector to obtain the probability distribution of the next word at each time step, and can select the most likely next word based on the probability distribution and add it to the generated text sequence. After each new word is generated, the context window can be updated to continue the reasoning process for the next word until the termination condition is reached. In the content generation model, the context window refers to the historical information or context range considered by the model when generating the next word. Afterwards, the content generation model can run an automated grammar and spelling checker to ensure that the generated script does not have obvious errors, and review the generated script based on the editing requirements description information to ensure that it meets the expected editing requirements.

[0048] In some optional embodiments, after the video generation tool obtains the copy information through the content generation model, it can display the copy information through the terminal device, and can optimize the copy information according to the user's editing operation on the copy information, which will not be repeated.

[0049] After acquiring the copywriting information based on the above implementation, in step 103, the video generation tool may output at least one candidate video template. Optionally, if the video generation tool runs on a terminal device or partially runs on a terminal device, when the video generation tool outputs at least one candidate video template, the at least one candidate video template may be displayed through the terminal device for the user to view. If the video generation tool runs on a server device, when the video generation tool outputs at least one candidate video template, the at least one candidate video template may be sent to a corresponding client program for display for the user to view.

[0050] In this embodiment, the at least one candidate video template is adapted to the editing requirement description information and / or the text information. Among them, any candidate video template is adapted to the editing requirement description information means that the candidate video template can meet the editing expectations corresponding to the editing requirement description information. Any candidate video template is adapted to the editing requirement description information means that the candidate video template can form a good visual and auditory aid for the text information, so as to achieve the expected publicity effect in a graphic and textual manner.

[0051] In some optional embodiments, before outputting at least one candidate video template, the video generation tool may select at least one candidate video template that is adapted to the editing requirement description information and / or the copywriting information from a plurality of preset video templates. Optionally, the plurality of preset video templates correspond to different styles respectively. If the editing requirement description information includes the script style, the video generation tool selects at least one candidate video template that is adapted to the script style from a plurality of video templates of different styles. Among them, the script style refers to the form of expression adopted by the script when narrating the content, including the plot structure, emotional tone, narrative atmosphere, and the design of visual and auditory elements. Optionally, the plurality of preset video templates carry corresponding style tags respectively, and the video generation tool may select the script style from the editing requirement description information, and perform tag matching between the script style and the style tags carried by the plurality of video templates. If a style tag that is adapted to the script style is matched, the video template corresponding to the style tag is used as a candidate video template. Based on this implementation mode, suitable candidate video templates can be recommended to users according to the script style expected by the users, thereby assisting users to make reasonable decisions quickly and further reducing the complexity of video editing.

[0052] Optionally, the video generation tool can identify the text attributes of the copy information and select at least one candidate video template that is adapted to the text attributes from multiple video templates. Among them, the text attributes of the copy information are used to describe the characteristics of the copy information in multiple dimensions, including but not limited to the content dimension, the physical dimension and the effect dimension. In some optional embodiments, the text attributes of the copy information may include but are not limited to: at least one of text length, content theme, keyword density and visual assistance requirements. Among them, the text length and keyword density are used to describe the characteristics of the copy information from the physical dimension. The longer the text length, the longer the video duration required for the video. The higher the keyword density, the higher the frequency of appearance of the video screen adapted to the keyword should be. The content theme is used to describe the characteristics of the copy information from the content dimension. Different content themes can be adapted to videos with different special effects or different rhythms. Visual assistance requirements are used to describe whether the copy information needs to be equipped with pictures, charts or other visual elements from the effect dimension to enhance the understanding of the copy information.

[0053] Optionally, the preset multiple video templates have a preset corresponding relationship with the text attribute. After identifying the text attribute of the copy information, the video generation tool can obtain the video template corresponding to the text attribute of the copy information according to the corresponding relationship between the multiple video templates and the text attribute, as the target video template. Based on this embodiment, after the copy information is generated, the user can be recommended a suitable candidate video template according to the text attribute of the copy information, which helps to make the selected target video template have a higher degree of adaptability with the copy information, thereby improving the overall video editing effect. After outputting at least one candidate video template, in step 104, the video generation tool can respond to the selection operation of at least one candidate video template, determine the selected target video template, and obtain the target video material adapted to the target video template. In this embodiment, the video material refers to the material required to generate the video, including but not limited to at least one of text, video clips, audio clips, pictures, graphics, plug-ins and animations. In this embodiment, the adaptation of the video material to the target video template means that the video material and the target video template are matched in at least one aspect such as duration, quantity, size and resolution.

[0054] Optionally, the target video material adapted to the target video template may include: at least one of a material provided by a user and a material acquired by the video generation tool from a material library.

[0055] Optionally, if the video generation tool runs on a terminal device or partially runs on a terminal device, when the video generation tool obtains the target video material that is compatible with the target video template, it can respond to the video material selection operation and obtain the video material selected by the user according to the material requirements corresponding to the target video template as the target video material. In this embodiment, the video generation tool can display a video material selection control through the terminal device, and respond to the user's trigger operation on the material selection control to access the material path specified by the user. The material path can be a local material path of the terminal device, or a material path located on a remote device, which is not limited in this embodiment. The video generation tool can display a list of materials under the material path, and can display the material requirements corresponding to the target video template and display the selection controls and submission controls corresponding to each material in the material path. The video generation tool can determine the video material selected by the user based on the user's selection operation on the selection control corresponding to the material, and respond to the user's trigger operation on the submission control to obtain the video material selected by the user as the target video material. Figure 3 As shown in the figure, the video generation tool can display the selection control of each material under the material path on the material selection page for the user to select, and display the prompt message "Please upload 5-9 videos" on the page. Figure 3 The displayed "Next" control confirms submission of the selected video material. Optionally, when the material selected by the user does not meet the material requirements corresponding to the target video template, the video generation tool can output modification prompt information to prompt the user to select the video material according to the material requirements corresponding to the target video template.

[0056] Based on this implementation, the video generation tool can provide users with an operation portal for selecting materials, so that users can flexibly submit the required video materials.

[0057] Optionally, the video generation tool can obtain video materials that are adapted to the editing requirement description information and / or the text information and meet the material requirements of the target video template from the material library as the target video material. In this embodiment, the material library can be a material library located locally on the terminal device or a material library located on a remote device (such as a remote server), and this embodiment is not limited. It should be noted that the video materials in the material library refer to video materials that are authorized for use. Optionally, in this embodiment, the video generation tool can perform keyword extraction on the editing requirement description information and / or the text information to obtain content keywords, and filter the video materials in the material library according to the content keywords and the material requirements of the target video template to obtain candidate materials. Afterwards, the video generation tool can filter out video materials with a relatively suitable length from the candidate materials according to the text length corresponding to the text information, and can further filter the video materials with a relatively suitable length according to the script style in the editing requirement description information to obtain the target video material. Based on this implementation, the video generation tool can automatically obtain the materials required for editing for the user, and can make the obtained materials as close as possible to the user's expected effect, which can further lower the technical threshold for video editing.

[0058] In some optional embodiments, the video generation tool can obtain video materials submitted by users according to the material requirements corresponding to the target video template as the target video material, and can obtain video materials that are adapted to the editing requirement description information and / or text information and meet the material requirements of the target video template from the material library as the target video material. In other words, the target video material used to edit the video includes both the material submitted by the user and the video material automatically obtained for the user by the video generation tool. The video material automatically obtained for the user by the video generation tool may include: opening material, ending material, transition material, and at least one of the atmosphere materials used to create an emotional atmosphere or visual style. The material submitted by the user and the video material automatically obtained by the video generation tool can be used in combination to complement each other to achieve a better video editing effect.

[0059] In some other embodiments, the video generation tool can also call the content generation model to generate video materials for users according to the material requirements, editing requirement description information and / or text information corresponding to the target video template, so as to further reduce the labor cost required for video editing. Optionally, the video generation tool can display a control in the material selection page, which is used to trigger the operation of AI generating video materials, such as Figure 3 The "AI helps me generate materials" control is shown. The video generation tool can respond to the triggering operation of the control and call the content generation model to generate video materials for the user, which will not be described in detail.

[0060] After obtaining the target video template and the target video material adapted to the target video template based on the above implementation, in step 105, the video generation tool can edit the text information and the video material according to the preset elements included in the target video template to obtain the target video.

[0061] In this embodiment, the preset elements included in the target video template refer to various components and attributes pre-set in the target video template, including timeline layout, placeholders, special effect elements, audio tracks, and subtitle styles, etc. These preset elements together constitute a complete video production framework. Among them, the timeline layout defines the timeline of the video from the beginning to the end, and is used to provide the structure of the video on the timeline, including scene transitions, segment duration, and overall duration. Placeholders are used to mark the insertion position of materials (such as video clips, pictures, text boxes, audio files) for filling materials in specific positions. Among them, special effect elements may include: transition effects, color themes, filters, etc. Among them, audio tracks are used to add background music. Subtitle styles are used to define the font, size, color, position, and appearance of subtitles, which is convenient for adding text descriptions or dialogue content.

[0062] In some optional embodiments, when the video generation tool edits the text information and video materials according to the preset elements contained in the target video template to obtain the target video, the video generation tool can fill the placeholders in the target video template with the video materials according to the timeline layout of the target video template to obtain the initial editing result. According to the subtitle style and / or audio style in the target video template, the text information is converted into subtitles and / or audio materials, and the subtitles and / or audio tracks corresponding to the imported audio materials are added to the initial editing result. According to at least one special effect element set in the target video template, special effects are added to the initial editing result. For example, according to the transition effect, transition effects can be added between different video elements, and color themes and filters can be added to some or all video elements, etc., which will not be repeated here.

[0063] In some optional embodiments, a video editing service may be run on the terminal device. When the video generation tool runs on the terminal device or partially runs on the terminal device, the video editing service may be directly called to edit the text information and video materials according to the preset elements contained in the target video template to obtain the target video. In other optional embodiments, the video editing service runs on the server device. If the video generation tool runs on the terminal device or partially runs on the terminal device, the video generation tool may call the video editing program running on the server device to edit the text information and video materials according to the preset elements contained in the target video template to obtain the target video, which will not be described separately.

[0064] Based on this implementation, in response to the video editing operation, the editing requirement description information can be obtained, the text information required for editing the video can be automatically generated according to the editing requirement description information, and at least one candidate video template adapted to the editing requirement description information and / or the text information can be output for the user to select. For the user, when there is a need for video editing, the video editing can be achieved by providing the editing requirement description information and selecting the target video template from the candidate video templates, and there is no need to manually perform complex editing operations with high technical thresholds in complex video editing pages. According to the target video template and the text information, the target video can be automatically edited for the user, which greatly reduces the labor cost and technical threshold required for video editing. When this video generation method with low labor cost and low technical threshold is applied to the domestic service scenario, it can enable more domestic practitioners to easily and efficiently create attractive promotional videos, thereby better promoting their services.

[0065] In some optional embodiments, the video generation tool may also export the target video to a specified path according to the user's video export operation for other processing, which is not limited in this embodiment.

[0066] It should be noted that, in some optional embodiments, when the video generation tool runs on a terminal device or partially runs on a terminal device, the video generation tool may also provide at least one operation entry for publishing a target video, and after the text information and video material have been edited and processed to obtain the target video, the "one-click publishing" of the target video can be achieved.

[0067] Optionally, the video generation tool may display at least one publishing control, and different publishing controls correspond to different social platforms. The video generation tool responds to the triggering operation of the target publishing control in the at least one publishing control, and publishes the target video to the target social platform through the interface of the social platform corresponding to the target publishing control. Furthermore, for the user, there is no need to export the video and jump to the target social platform to perform the video publishing operation, and the target video can be quickly published.

[0068] Optionally, before the user publishes the target video, the video generation tool can also construct review prompts based on the target video and the editing requirement description information, and call the large language model based on the review prompts to review whether the target video is compatible with the editing requirement description information. If the target video is compatible with the editing requirement description information, it can be considered that the target video meets the user's expected effect, and the video generation tool can publish the target video to the target social platform through the interface of the social platform corresponding to the target publishing control. Based on this implementation method, the quality of the target video can be automatically reviewed before the target video is published, thereby ensuring that the published target video can meet the expected effect.

[0069] It should be noted that the execution subject of each step of the method provided in the above embodiment can be the same device, or the method can be executed by different devices. For example, the execution subject of steps 101 to 104 can be device A; for another example, the execution subject of steps 101 and 102 can be device A, and the execution subject of step 103 can be device B; and so on.

[0070] In addition, in some of the processes described in the above embodiments and the accompanying drawings, multiple operations that appear in a specific order are included, but it should be clearly understood that these operations may not be executed in the order in which they appear in this article or executed in parallel, and the sequence numbers of the operations, such as 101, 102, etc., are only used to distinguish between different operations, and the sequence numbers themselves do not represent any execution order. In addition, these processes may include more or fewer operations, and these operations may be executed in sequence or in parallel. It should be noted that the descriptions of "first", "second", etc. in this article are used to distinguish different messages, devices, modules, etc., do not represent the order of precedence, and do not limit the "first" and "second" to be different types.

[0071] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with the relevant laws, regulations and standards of the relevant countries and regions, and provide corresponding operation entrances for users to choose to authorize or refuse.

[0072] In addition, it should be noted that, in the case where the embodiments of the present application involve user interaction operations or trigger operations, the user interaction operations or trigger operations involved in the embodiments of the present application include but are not limited to: touch operation, gesture operation, voice operation, head movement operation, eye movement operation and other interactive operations in various ways; among which, touch operation includes but is not limited to: click operation, double-click operation, long press operation, sliding operation, pinch operation or mouse hover operation, etc. Sliding operation includes but is not limited to: straight line sliding, curve sliding, etc.

[0073] Figure 4 FIG. 1 is a schematic diagram showing the structure of an electronic device provided by an exemplary embodiment of the present application, and the electronic device is applicable to the video generation method provided by the above-mentioned embodiment. Figure 4 As shown, the electronic device includes: a memory 401 and a processor 402 .

[0074] The memory 401 is used to store computer programs and can be configured to store various other data to support operations on the electronic device. Examples of such data include instructions for any application program or method operating on the electronic device.

[0075] The processor 402 is coupled to the memory 401 and is used to execute the computer program in the memory 401, so as to: respond to a video editing operation, obtain editing requirement description information, and the editing requirement description information is used to describe the expected editing effect from multiple dimensions; according to the editing requirement description information, call a content generation model to generate text information required for editing the video; output at least one candidate video template, and the at least one candidate video template is adapted to the editing requirement description information and / or the text information; in response to a selection operation of the at least one candidate video template, determine a selected target video template, and obtain a target video material adapted to the target video template; according to the preset elements contained in the target video template, edit the text information and the target video material to obtain a target video.

[0076] Optionally, when obtaining the editing requirement description information, the processor 402 is specifically used to: obtain a voice message input by a user, and parse information associated with the video editing requirement from the voice message to obtain the editing requirement description information; or, display a text configuration page, and obtain the editing requirement description information based on the user's configuration operations on the text configuration page.

[0077] Optionally, when the processor 402 displays the copy configuration page and obtains the editing requirement description information based on the configuration operations of the user on the copy configuration page, it is specifically used to: display multiple configuration items on the copy configuration page, and the multiple configuration items include: store logo, script style, service direction, service type, service area and service advantages; according to the configuration operations of the user on the multiple configuration items on the copy configuration page, obtain the configuration content of each of the multiple configuration items as the editing requirement description information.

[0078] Optionally, when the processor 402 calls the content generation model according to the editing requirement description information to generate the copy information required for editing the video, it is specifically used to: convert the configuration content of each of the multiple configuration items into structured prompt words according to the structure of the multiple configuration items in the copy configuration page; and call the content generation model according to the structured prompt words so that the content generation model generates the copy information according to the structured prompt words.

[0079] Optionally, before displaying at least one candidate video template, the processor 402 is also used to: if the editing requirement description information includes a script style, select at least one candidate video template that is adapted to the script style from multiple video templates of different styles; and / or, identify text attributes of the copy information, and select at least one candidate video template that is adapted to the text attributes from the multiple video templates, wherein the text attributes include: text length, content theme, keyword density, and at least one of visual aid requirements.

[0080] Optionally, when acquiring the target video material that is adapted to the target video template, the processor 402 is specifically used to: respond to a video material selection operation, acquire the video material submitted by the user according to the material requirements corresponding to the target video template, as the target video material; and / or, acquire, from the material library, the video material that is adapted to the editing requirement description information and / or the text information and meets the material requirements of the target video template, as the target video material.

[0081] Optionally, when the processor 402 edits the text information and the target video material according to the preset elements contained in the target video template to obtain the target video, it is specifically used to: fill the placeholders in the target video template with the target video material according to the timeline layout of the target video template to obtain an initial editing result; convert the text information into subtitles and / or audio materials according to the subtitle style and / or audio style in the target video template, and add the subtitles and / or import the audio track corresponding to the audio material to the initial editing result; and, add special effects to the initial editing result according to at least one special effect element set in the target video template.

[0082] Optionally, after the processor 402 edits the text information and the target video material according to the preset elements included in the target video template to obtain the target video, it is also used to: display at least one publishing control, different publishing controls corresponding to different social platforms; respond to a triggering operation of a target publishing control in the at least one publishing control, and publish the target video to the target social platform through the interface of the social platform corresponding to the target publishing control.

[0083] Further, if Figure 4 As shown, the electronic device also includes: a communication component 403, a power component 404, a display component 405, an audio component 406 and other components. Figure 4 Only some components are shown schematically, which does not mean that the electronic device only includes Figure 4 Components shown. Figure 4Components in the dashed box are optional components, not mandatory components, and may depend on the product form of the electronic device. The electronic device of this embodiment may be implemented as a terminal device such as a desktop computer, a laptop computer, a smart phone, or an IOT device, or may be a server device such as a conventional server, a cloud server, or a server array. If the electronic device of this embodiment is implemented as a terminal device such as a desktop computer, a laptop computer, a smart phone, etc., it may include Figure 4 If the electronic device of this embodiment is implemented as a server device such as a conventional server, a cloud server or a server array, it may not include Figure 4 Components within the dashed box.

[0084] Among them, the memory 401 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk or optical disk.

[0085] The communication component 403 is configured to facilitate wired or wireless communication between the device where the communication component is located and other devices. The device where the communication component is located can access a wireless network based on a communication standard, such as Wi-Fi (wireless network communication technology), 2G (such as Global System for Mobile Communications (GSM)), 3G (such as Wideband Code Division Multiple Access (WCDMA), 4G (such as Long Term Evolution (LTE)), 4G+ (such as upgraded Long Term Evolution (LTE-Advanced, LTE-A)) or 5G (5th Generation Mobile Communication Technology), or a combination thereof. In an exemplary embodiment, the communication component receives a broadcast signal or broadcast-related information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communication component can be implemented based on Near Field Communication (NFC) technology, Radio Frequency Identification (RFID) technology, Infrared Data Association (IrDA) technology, Ultra Wide Band (UWB) technology, Bluetooth (BT) technology and other technologies.

[0086] The power supply component 404 is used to provide power to various components of the device where the power supply component is located. The power supply component may include a power management system, one or more power supplies, and other components associated with generating, managing and distributing power to the device where the power supply component is located.

[0087] The display assembly includes a screen, which may include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive input signals from a user. The touch panel includes one or more touch sensors to sense touch, slide, and gestures on the touch panel. The touch sensor may not only sense the boundaries of a touch or slide action, but also detect the duration and pressure associated with the touch or slide operation.

[0088] The audio component may be configured to output and / or input audio signals. For example, the audio component includes a microphone (MIC), and when the device where the audio component is located is in an operating mode, such as a call mode, a recording mode, and a speech recognition mode, the microphone is configured to receive an external audio signal. The received audio signal may be further stored in a memory or sent via a communication component. In some embodiments, the audio component also includes a speaker for outputting an audio signal.

[0089] In this embodiment, the electronic device can respond to the video editing operation, obtain the editing requirement description information, automatically generate the text information required for editing the video according to the editing requirement description information, and output at least one candidate video template adapted to the editing requirement description information and / or the text information for the user to select. For the user, when there is a need for video editing, the video editing can be realized by providing the editing requirement description information and selecting the target video template from the candidate video templates, and there is no need to manually perform complex and technically demanding editing operations in a complex video editing page. According to the target video template and the text information, the target video can be automatically edited for the user, which greatly reduces the labor cost and technical threshold required for video editing. When this video generation method is applied to the domestic service scenario, it can enable more domestic practitioners to easily and efficiently create attractive promotional videos, thereby better promoting their services.

[0090] Accordingly, an embodiment of the present application further provides a computer-readable storage medium storing a computer program, which, when executed, can implement each step that can be executed by an electronic device in the above method embodiment.

[0091] The embodiment of the present application also provides a computer program product, including: a computer program / instructions, which, when executed by a processor, can implement the steps in the method provided in the embodiment of the present application.

[0092] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM (Compact Disc Read-Only Memory, read-only optical disc read-only memory), optical storage, etc.) containing computer-usable program codes.

[0093] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0094] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0095] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0096] In a typical configuration, a computing device includes one or more processors (Central Processing Unit, CPU), input / output interface, network interface and memory.

[0097] The memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0098] Computer-readable media include permanent and non-permanent, removable and non-removable media that can be used to store information by any method or technology. Information can be computer-readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, Parallel Random Access Machine (PRAM), Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, CD-ROM, Digital Video Disc (DVD) or other optical storage, magnetic cassettes, disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer-readable media does not include temporary computer-readable media (transitory media), such as modulated data signals and carrier waves.

[0099] It should also be noted that the terms "comprises", "includes" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, product or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, product or device. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the presence of other identical elements in the process, method, product or device including the element.

[0100] The above is only an embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.

Claims

1. A video generation method, characterized in that: include: In response to the video editing operation, obtaining editing requirement description information, wherein the editing requirement description information is used to describe the expected editing effect from multiple dimensions; According to the editing requirement description information, a content generation model is called to generate text information required for editing the video; Outputting at least one candidate video template, wherein the at least one candidate video template is adapted to the editing requirement description information and / or the text information; In response to the selection operation of the at least one candidate video template, determining a selected target video template, and acquiring a target video material adapted to the target video template; According to the preset elements included in the target video template, the text information and the target video material are edited to obtain the target video.

2. The method according to claim 1, characterized in that Get the description of the editing requirements, including: Acquire a voice message input by a user, and parse the voice message to obtain information associated with the video editing requirement to obtain the editing requirement description information; or, The copy configuration page is displayed, and the editing requirement description information is obtained according to the configuration operation of the user on the copy configuration page.

3. The method according to claim 2, characterized in that Displaying a copy configuration page, and obtaining the editing requirement description information according to the configuration operation of the user on the copy configuration page, including: Displaying multiple configuration items on the copywriting configuration page, the multiple configuration items including: store logo, script style, service direction, service type, service area and service advantages; According to the configuration operation of the user on the multiple configuration items on the document configuration page, the configuration contents of each of the multiple configuration items are obtained as the editing requirement description information.

4. The method according to claim 3, characterized in that According to the editing requirement description information, the content generation model is called to generate the text information required for editing the video, including: According to the structure of the multiple configuration items in the copy configuration page, convert the configuration content of each of the multiple configuration items into a structured prompt word; The content generation model is called according to the structured prompt words, so that the content generation model generates the copy information according to the structured prompt words.

5. The method according to any one of claims 1 to 4, characterized in that: Before displaying at least one candidate video template, the method further includes: If the editing requirement description information includes a script style, then selecting at least one candidate video template that is adapted to the script style from a plurality of video templates of different styles; and / or, Identify the text attributes of the copy information, and select at least one candidate video template adapted to the text attributes from the multiple video templates, wherein the text attributes include at least one of text length, content theme, keyword density, and visual assistance requirements.

6. The method according to any one of claims 1 to 4, characterized in that: Acquiring a target video material adapted to the target video template, including: In response to the video material selection operation, obtaining the video material submitted by the user according to the material requirement corresponding to the target video template as the target video material; and / or, From the material library, video material that is adapted to the editing requirement description information and / or the text information and meets the material requirements of the target video template is obtained as the target video material.

7. The method according to any one of claims 1 to 4, characterized in that: According to the preset elements contained in the target video template, the text information and the target video material are edited to obtain the target video, including: According to the timeline layout of the target video template, the placeholders in the target video template are filled with the target video material to obtain an initial editing result; According to the subtitle style and / or audio style in the target video template, convert the text information into subtitles and / or audio materials, and add the subtitles and / or import the audio tracks corresponding to the audio materials into the initial editing results; and According to at least one special effect element set in the target video template, special effects are added to the initial editing result.

8. The method according to any one of claims 1 to 4, characterized in that: According to the preset elements contained in the target video template, the text information and the target video material are edited to obtain the target video, and the method further includes: Display at least one publishing control, where different publishing controls correspond to different social platforms; In response to a triggering operation on a target publishing control among the at least one publishing control, the target video is published on the target social platform through an interface of the social platform corresponding to the target publishing control.

9. An electronic device, characterized in that: include: Memory and processor; The memory is used to store one or more computer instructions; The processor is configured to execute the one or more computer instructions to: perform the steps in the method according to any one of claims 1-8.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps in the method described in any one of claims 1 to 8 can be implemented.

11. A computer program product, characterized in that include: A computer program / instruction, which, when executed by a processor, can implement the steps of the method according to any one of claims 1 to 8.

Images